zedline5
154 posts







football AI code is finally open-source - player detection and tracking - team clustering - camera calibration I still need to work on README; don't judge me on that code: github.com/roboflow/sports


[NeurIPS '24] Generalizable and Animatable Gaussian Head Avatar Remark: Runs at 67 fps as reported and comes with code🤯 Contributions: • We propose GAGAvatar, which to our knowledge is the first generalizable 3D Gaussian head avatar framework that achieves single forward reconstruction and real-time reenactment. • To achieve this, we propose a dual-lifting method to lift Gaussians from a single image and introduce a method that uses 3DMM priors to constrain the lifting process. • We combine 3DMM priors and 3D Gaussians to accurately transfer expression information while avoiding redundant computations.

My next plan for Photo AI is talking people: - add ElevenLabs TTS - add video lipsync That potentially moves it from "fun little app" to "useful B2B product" as companies can use it for: - video ads with talking people - education or explainer videos - talking AI influencers A la HeyGen but 100% AI, which means: - put yourself or your presenter or your influencer in any place/time/event in seconds - let them speak about anything while being there - no need to record training videos like HeyGen, just upload 10 photos No idea if that works but let's try!


@levelsio Love the DIY approach! Reminds me of the early internet days. How long did it take to set all this up?











